Llama 3 70B Instruct abliterated Model Card This is meta llama/Llama 3 70B Instruct with orthogonalized bfloat16 safetensor weights, generated with the methodology that was described in the preview paper/blog post: 'Refusal in LLMs is mediated by a single direction' which I encourage you to read to understand more. TL;DR: this model has had certain weights manipulated to "inhibit" the model's ability to express refusal. It is not in anyway guaranteed that it won't refuse you, understand your request, it may still lecture you about ethics/safety, etc. It is tuned in all other respects the same as the original 70B instruct model was, just with the strongest refusal direction orthogonalized out. Quants GGUF Quants available here For the people who like tinkering or looking to save bandwidth In the repo, I've included refusal dir.pth If you have Llama 3 70B Instruct model downloaded already, you can use the ortho cookbook to apply it to your downloaded model, which will make it the same as what you'd download from here. Quirkiness awareness notice This model may come with interesting quirks, as I obviously haven't extensively tested it, and the methodology being so new. I encourage you…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy